Simon Gardling

Ok then, Thanks!

> I would like to know this too. I've been looking for alternatives but have been unable to find any good alternatives. Mimalloc doesn't work unless one uses emscripten [purpleprotocol/mimalloc_rust#76...

Is this not happening?

What does this aim to achieve/solve?

> [ggerganov/llama.cpp#2059](https://github.com/ggerganov/llama.cpp/pull/2059) got merged That backend seems to be more performant and works on more hardware including Intel GPUs.

same issue

sad that nvidia is only supported on so many machine learning projects :(

@JABirchall I did not know that, I have a 6900xt though haha.

They're not even opensource and you can't even access it. I don't expect support for a while if ever. Edit: this has changed

> The first download links have been distributed by Facebook earlier today. I've already seen a torrent on twitter - oh my! Wish they simply uploaded it to huggingface :(